6 papers
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
Mingqiao Ye, Zhaochong An, Zhitong Gao +11
Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-language models, and increasingly…
Weblica: Scalable and Reproducible Training Environments for Visual Web Agents
OÄuzhan Fatih Kar, Roman Bachmann, Yuanzheng Gong +2
The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection attempts remain limited to off…
How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
Rahul Ramachandran, Ali Garjani, Roman Bachmann +3
Multimodal foundation models (MFMs), such as GPT-4o, have recently made remarkable progress. However, their detailed visual understanding beyond question answering remains unclear.…
(1D) Ordered Tokens Enable Efficient Test-Time Search
Zhitong Gao, Parham Rezaei, Ali Cy +7
Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information,…
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
Andrei Atanov, Jesse Allardice, Roman Bachmann +6
Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and…
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
Roman Bachmann, Jesse Allardice, David Mizrahi +6
Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixel…